본문 바로가기
  • Home
Basic Search

An Experimental Study on Multi-Document Summarization for Question Answering

  • Journal of the Korean Society for Information Management
  • Abbr : JKOSIM
  • 2004, 21(3), pp.289~303
  • DOI : 10.3743/KOSIM.2004.21.3.289
  • Publisher : 한국정보관리학회
  • Research Area : Interdisciplinary Studies > Library and Information Science
  • Received : August 27, 2004
  • Accepted : September 13, 2004
  • Published : September 30, 2004

Sanghee Choi ORD ID 1,  Young-Mee Chung 2

1대구가톨릭대학교
2연세대학교

Accredited

ABSTRACT

This experimental study proposes a multi-document summarization method that produces optimal summaries in which users can find answers to their queries. In order to identify the most effective method for this purpose, the performance of the three summarization methods were compared. The investigated methods are sentence clustering, passage extraction through spreading activation, and clustering-passage extraction hybrid methods. The effectiveness of each summarizing method was evaluated by two criteria used to measure the accuracy and the redundancy of a summary. The passage extraction method using the sequential bnb search algorithm proved to be most effective in summarizing multiple documents with regard to summarization precision. This study proposes the passage extraction method as the optimal multi-document summarization method.

Journal Copyright Policy

BY-NC-ND 아이콘

This license enables reusers to copy and distribute the material in any medium or format in unadapted form only, for noncommercial purposes only, and only if attribution is given to the creator.

Statistics

  • 421 Viewed
  • 210 Downloaded

Tools

Issue List

Citation status

* References for papers published after 2025 are currently being built.

Basic Search Advanced Search